INDEX

Explanations

even

np_max-act · gemini-2.0-flash

The neuron fires most strongly on short adverbs and discourse markers that add emphasis—words like “even,” “only,” “just,” and similar intensifiers.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

Ads

-0.07

axis

-0.06

 King

-0.06

rá

-0.06

 coder

-0.06

 raining

-0.06

ale

-0.06

 capability

-0.06

POSITIVE LOGITS

"g

0.07

 zorunda

0.06

今天

0.06

 نقد

0.06

 которого

0.06

[Math

0.06

(sequence

0.06

/testify

0.06

ніч

0.06

imm

0.06

Activations Density 0.014%

even

The neuron fires most strongly on short adverbs and discourse markers that add emphasis—words like “even,” “only,” “just,” and similar intensifiers.

No Comments

No Known Activations

even

The neuron fires most strongly on short adverbs and discourse markers that add emphasis—words like “even,” “only,” “just,” and similar intensifiers.

No Comments

No Known Activations